[newfocogi]

TLDR: Quantized versions of Llama 3.2 1B and 3B models with "competitive accuracy" to the original versions (meaning some degraded performance; plots included in the release notes).

[newfocogi]

Quantization schemes include post-training quantization (PTQ), SpinQuant, and QLoRA.

[grahamj]

Thx, I prefer not to visit meta properties :X

They were already pretty small but I guess the smaller the better as long as accuracy doesn't suffer too much.